Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4842 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.8137. Min Act: -0.0000

Data Index: 310155 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.7415. Min Act: -0.0000

Data Index: 447365 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.8323. Min Act: -0.0000

Data Index: 1262780 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.6987. Min Act: 0.0000

Data Index: 1047138 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.6653. Min Act: -0.0000

Data Index: 638269 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.6139. Min Act: -0.0000

Data Index: 361563 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.5981. Min Act: -0.0000

Data Index: 340155 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.5698. Min Act: -0.0000

Data Index: 584124 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.5324. Min Act: -0.0000

Data Index: 655655 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.5076. Min Act: 0.0001

Data Index: 71058 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.5046. Min Act: -0.0000

Data Index: 1347173 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.4828. Min Act: -0.0000

Data Index: 1103309 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.5109. Min Act: 0.0000

Data Index: 1264331 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.4977. Min Act: -0.0000

Data Index: 341763 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.5140. Min Act: -0.0000

Data Index: 1178476 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.4708. Min Act: -0.0000

Data Index: 395639 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.5038. Min Act: 0.0001

Data Index: 531544 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.4776. Min Act: -0.0000

Data Index: 381140 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.4602. Min Act: -0.0000

Data Index: 654968 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.4687. Min Act: 0.0000

Data Index: 1063710 (C4 (Web Text))

Max Activating Token Index: 352